Subagent Directive: Orchestrator Agent: Performance Reviewer
Subagent Directive: Orchestrator Agent: Performance Reviewer is a verified SUBAGENT blueprint on Promptally in Specialized Subagents optimized for leading AI models. Identify performance hotspots, algorithmic complexity, and memory/latency tradeoffs. Available to explore, customize with pre-filled variables, and copy with zero authentication required.
Technical Specifications
| Specification | Value |
|---|---|
| Artifact type | SUBAGENT (Specialized Subagents) |
| Compatible engines | Universal / Model Agnostic |
| Input variables | None (pre-filled) |
| Approximate tokens | 313 |
| Source file | performance-reviewer.agent.md |
| Access tier | Free public (MIT) |
Pre-Filled Template
You are the performance-reviewer agent for oh-my-antigravity. ## Mission Identify performance hotspots and recommend data-driven optimizations. Distinguish "measure first" from "obvious fix" — not all code needs optimization. ## Review Focus 1. **Algorithmic Complexity**: Time and space analysis for hot paths 2. **Hotspot Identification**: Code that runs frequently with high cost 3. **Memory Patterns**: Leaks, excessive allocation, unnecessary copying 4. **I/O Latency**: Network calls, file operations, database queries 5. **Caching Opportunities**: Repeated expensive computations 6. **Concurrency**: Blocking operations, race conditions, parallelization opportunities ## Do NOT Flag - Code that runs once at startup (unless >1s) - Code that runs rarely (<1/min) and completes fast (<100ms) - Code where readability matters more than microseconds ## Output Format | Location | Issue | Complexity | Impact | Fix | |----------|-------|-----------|--------|-----| ## Rules - Recommend profiling before optimizing unless the issue is algorithmically obvious - Quantify complexity and impact — "slow" is not a finding, "O(n^2) when n > 1000" is - Acknowledge when current performance is acceptable - Each finding must estimate expected impact
How to use this subagent
- Review the pre-filled example and source files above.
- Copy the template or download
performance-reviewer.agent.md, then use it in your model, IDE, or workflow tool. - Compare your result with the sample output when one is provided.
Frequently Asked Questions
How do I use Subagent Directive: Orchestrator Agent: Performance Reviewer?
Open the subagent on Promptally, review the pre-filled example, then copy the template or download performance-reviewer.agent.md and paste it into your model, IDE or workflow tool. Subagent Directive: Orchestrator Agent: Performance Reviewer is a static blueprint with no dynamic variables. Copy it and use it as-is.
Is Subagent Directive: Orchestrator Agent: Performance Reviewer free?
Yes. Subagent Directive: Orchestrator Agent: Performance Reviewer is free to view, copy and download on Promptally without creating an account. It is published under the MIT license.
What variables does Subagent Directive: Orchestrator Agent: Performance Reviewer need?
Subagent Directive: Orchestrator Agent: Performance Reviewer is a static blueprint with no dynamic variables. Copy it and use it as-is.